Customer targeting

Churn scoring

Know which customers are ready to churn while there's still time to save them — using BigQuery

You’ll need a Faraday account to use this template. It’s free to sign up and you can use sample data to start.

As a Faraday user, you might find Churn scoring predictions in BigQuery particularly useful because it seamlessly integrates with the tools you’re already comfortable with. If you're already leveraging BigQuery for your data warehousing, adding churn predictions to the mix can give you a clearer picture of which customers are at risk of leaving, all within a familiar environment. This allows you to quickly and effectively take action based on insights that are right at your fingertips. It’s a handy way to consolidate your workflows and make more informed decisions without having to jump between different platforms.

Step 1
Connect your data sources
Use the link below to connect BigQuery to Faraday. You can also skip this step and use CSV files to get started instead.
BigQuery
Step 2
Ingest your data into event streams
This allows Faraday to understand what your data means. These links will guide you through ingesting the data necessary to power this template.
Transaction Cancellation
Step 3
Organize your customer data
You'll create groups, called cohorts, that are the essential building blocks of Faraday and allow you to easily predict any customer behavior.
Customers Churned customers
Step 4
Declare your prediction objectives
With your cohorts defined, it's easy to instruct Faraday to predict the necessary behaviors. Follow the docs with the link below.
Likelihood to churn
Step 5
Define your churn scoring pipeline and deploy to BigQuery
Finally, deploy your prediction with the link below.
Churn scoring
Step 6
Deploy to BigQuery
Create a deployment target using the BigQuery connection you created above. Or, get started by simply deploying to CSV.
BigQuery